MadryLab / modelcomponentsLinks
Decomposing and Editing Predictions by Modeling Model Computation
☆139Updated last year
Alternatives and similar repositories for modelcomponents
Users that are interested in modelcomponents are comparing it to the libraries listed below
Sorting:
- Official implementation of MAIA, A Multimodal Automated Interpretability Agent☆99Updated last month
- [ICCV 2025] Auto Interpretation Pipeline and many other functionalities for Multimodal SAE Analysis.☆165Updated 2 months ago
- Official PyTorch Implementation for Vision-Language Models Create Cross-Modal Task Representations, ICML 2025☆31Updated 7 months ago
- ☆33Updated 11 months ago
- PyTorch library for Active Fine-Tuning☆95Updated 2 months ago
- Official implementation of Phi-Mamba. A MOHAWK-distilled model (Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Mode…☆116Updated last year
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆84Updated last year
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆41Updated last year
- Code accompanying the paper "Massive Activations in Large Language Models"☆187Updated last year
- Official code for the ICML 2024 paper "The Entropy Enigma: Success and Failure of Entropy Minimization"☆55Updated last year
- ☆89Updated last year
- Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch☆180Updated 5 months ago
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆143Updated 5 months ago
- [COLING'25] Exploring Concept Depth: How Large Language Models Acquire Knowledge at Different Layers?☆82Updated 10 months ago
- ☆51Updated last year
- ☆200Updated last year
- ☆145Updated last year
- A curated list of Model Merging methods.☆94Updated last week
- [ICML 2025] Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction☆80Updated 6 months ago
- Official PyTorch Implementation of "The Hidden Attention of Mamba Models"☆231Updated last month
- Sparse and discrete interpretability tool for neural networks☆64Updated last year
- An AI benchmark for creative, human-like problem solving using Sudoku variants☆141Updated last month
- Towards Understanding the Mixture-of-Experts Layer in Deep Learning☆33Updated last year
- Official repository of "LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging"☆31Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆151Updated 5 months ago
- ☆242Updated last year
- One Initialization to Rule them All: Fine-tuning via Explained Variance Adaptation☆45Updated last month
- Official Code for Paper: Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation☆130Updated 5 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆186Updated 7 months ago
- [NeurIPS 2024] Official Repository of The Mamba in the Llama: Distilling and Accelerating Hybrid Models☆232Updated last month